© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15271
    Prev
    Next
    INDEX
    Explanations

    c/c++ syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOLE
    -0.07
    ئÙĨ
    -0.07
    /cop
    -0.06
    ibble
    -0.06
    ervals
    -0.06
     ReiÃŁ
    -0.06
    antom
    -0.06
    iant
    -0.06
    æľīæĦı
    -0.06
    ä¸ĢæĪIJ
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.07
    渣
    0.07
     twice
    0.07
    èĢĮéĿŀ
    0.07
     squared
    0.07
    ular
    0.07
     vs
    0.07
    emn
    0.07
    Ai
    0.07
    ార
    0.06
    Activations Density 0.009%

    No Known Activations